# GPT-4 with vision available

**URL:** <https://meta.discourse.org/t/gpt-4-with-vision-available/295462>\
**Category:** Feature\
**Tags:** ai, ai-bot\
**Created:** [February 15, 2024, 11:32am UTC](https://meta.discourse.org/t/gpt-4-with-vision-available/295462 "2024-02-15T11:32:21Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![sam](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/sam/32/102149_2.png) [@sam](https://meta.discourse.org/u/sam)\
**Post date:** [February 15, 2024, 10:08pm UTC](https://meta.discourse.org/t/gpt-4-with-vision-available/295462/6 "2024-02-15T22:08:07Z")

</div>

At the moment `gpt-4-turbo` == `gpt-4-0125-preview` aka no vision.

@keegan is exploring some vision integration here:

> <https://github.com/discourse/discourse-ai/pull/470>
>
> This PR adds a new feature where you can generate captions for images in the com…poser using AI.
> 
> \## Preview
> 
> https://github.com/discourse/discourse-ai/assets/30090424/f5a7deb4-2eb4-41dd-9efb-134a225ba5d4

Particularly adding captions to images via vision apis (both open and closed models)

I do really like the “demo” power of … starting a PM with bot, uploading an image and asking about it, but need to think through flow cause we would need to switch in and out of models.

Maybe a concept of “auto tool” can work here, so if we see an upload we automatically route to tool and then back to the main model… will have a think.

Technically wiring this up is not too complex within our architecture.

---

_[View the full topic](https://meta.discourse.org/t/gpt-4-with-vision-available/295462)._